Genomic Prediction Performance for Chicken Body Weight and Abdominal Fat

Additional file 3 from a 2026 study by Ranran Zhu compares LightGBM and AdaBoost.R2 models for predicting key production traits in chickens. The 11.9 KB XLSX file contains performance metrics based on 10 repeats of 5-fold cross-validation for body weight and abdominal fat at different growth stages. It is shared under a CC-BY-4.0 license on figshare.

Use Cases

• Benchmarking LightGBM and AdaBoost.R2 model performance based on the described cross-validation results.
• Analyzing genomic prediction accuracy for body weight (BW) across different chicken growth stages.
• Comparing model performance for predicting abdominal fat thickness (AFT) in poultry.
• Assessing the stability of prediction models based on the 10 repeated cross-validation runs.

Strengths

• Performance metrics are derived from a structured 10 repeats of 5-fold cross-validation protocol.
• Data is openly shared under a permissive CC-BY-4.0 license.
• The file is small (11.9 KB), ensuring quick download and inspection.

Limitations

• Row count and specific column definitions are unknown, requiring manual inspection after download.
• The description is limited to the file's purpose; detailed data semantics must be inferred from the XLSX file itself.

Provenance

Source

Ranran Zhu via figshare.

Collection Method

Likely generated as supplementary material from a comparative analysis of machine learning models for genomic prediction.

Freshness

Last updated 2026-04-25 03:37:57.